Apparatus and a method for reducing red-eye in a digital image

• US 6,016,354 A
• Filed: 10/23/1997
• Issued: 01/18/2000
• Est. Priority Date: 10/23/1997
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Company (HP Inc.)
• Inventors: Tretter, Daniel R., Konstantinides, Konstantinos, Patti, Andrew, Lin, Qian
• Primary Examiner(s): Kelley, Christopher S.
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US08/956,380
• Time in Patent Office: 817 Days
• Field of Search: 382/117, 382/115, 382/167, 382/162, 382/164, 382/168, 382/169, 382/171, 382/172, 358/500, 358/520, 358/527, 358/518
• US Class Current: 382/117
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A red-eye reduction system is described that includes a masking module. The masking module converts an image into a mask having first state areas representing red color pixels of the image and second state areas representing other color pixels of the image. The image includes an eye with a red pupil. A pupil locating module is coupled to the masking module to locate a substantially first state area in the mask that resembles a pupil. A color replacing module is then coupled to the pupil locating module to change the red color pixels in the area into monochrome (grey) or other predefined colors. The color replacing module also adjusts the boundary of the area by changing the colors of pixels in close proximity to the area if the color of these pixels is determined to be sufficiently close to red such that natural appearance of the eye is maintained when reducing the red pupil. A method of reducing red-eye effect in a digital image is also described.

Claims

1. A red-eye reduction system, comprising:

(A) a masking module that converts an image into a mask having first state areas representing red color pixels and second state areas representing other color pixels, wherein the image includes an eye with a red pupil;

(B) a pupil locating module coupled to the masking module to locate a substantially first state area in the mask that resembles a pupil by determining if the substantially first state area is a substantially largest first state area within the mask, wherein determining that substantially first state area resembles a pupil, the pupil locating module modifies the mask by changing all other first state areas in the mask into second state such that the modified mask only has the substantially first state areas;

(C) a color replacing module coupled to the pupil locating module to change the red color pixels in the area into a predetermined color, wherein the color replacing module also adjust boundary of the area by changing the colors of pixels in close proximity to the, area to the predetermined color if the color of these pixels is determined to be sufficiently close to red.

2. The red-eye reduction system of claim 1, wherein the substantially first state area includes a second state area within the first state area, wherein the second state area represents the glint in the pupil.

3. The red-eye reduction system of claim 2, wherein the predetermined color is a zero chrominance, wherein the color replacing module also changes the luminance value of all pixels within the substantially first state area by a predetermined factor.

4. The red-eye reduction system of claim 1, wherein the masking module converts the image into the mask by first raising red-green-blue values of the image to a predetermined power and then performing a standard luminance-chrominance conversion.

5. The red-eye reduction system of claim 1, wherein the color replacing module determines if the color of the adjacent pixel is sufficiently close to red by comparing the color value of the adjacent pixel with (i) a median red value and (ii) a median green value of all the red color pixels within the substantially first state area.

6. The red-eye reduction system of claim 1, wherein the adjacent pixel is a pixel that has at least one neighboring pixel in the substantially first state area.

7. A method of reducing red-eye effect in a digital image, comprising:

(A) converting an image having an eye with a red pupil into a binary mask having first state areas representing red color pixels of the image and second state areas representing other color pixels of the image, wherein the image includes an eye with a red pupil;

(B) processing the mask to locate a substantially first state area in the mask that resembles a pupil,

(C) changing the red color pixels in the area into a predetermined color with boundary adjustments such that the color of pixels in close proximity to the area is also changed to the predetermined color if the color of these pixels is determined to be sufficiently close to red other comprising

(a) determining if the adjusted pixel outside the substantially first state area is a pixel that has at least one neigh-boring pixel within the substantially first state area;

(b) if so, comparing the color value of the adjusted pixel with (i) a median red value and (ii) a median green value of all tile red color pixels within the substantially first state area to determine if the color of the adjusted pixel is sufficiently close to red, wherein the color value of the adjusted pixel is determined to be sufficiently close to red if the color value of the adjusted pixel varies from the median red value by less than a first predetermined value and the red-green color difference of the adjusted pixel varies from the difference between the red Median value and the green median value by less than a second predetermined value;

(c) if so, changing the color of the adjacent pixel to the predetermined color.

8. The method of claim 7, wherein the step (B) further comprises the steps of

(I) determining if the substantially first state area is a largest substantially first state area in the mask;

(II) determining if the substantially first state area is substantially circular;

(III) modifying the mask by changing all other first state areas in the mask into second state such that the modified mask only has the substantially first state area.

9. The method of claim 7, wherein the substantially first state area includes a second state area within the first state area, wherein the second state area represents the glint in the pupil.

10. The method of claim 7, wherein the step (C) further comprises the steps of

(a) changing the color of the red color pixels within the substantially first state area to the predetermined color by setting the chrominance of the red color pixels to zero;

(b) changing the luminance value of all pixels within the substantially first state area by a predetermined factor.

11. The method of claim 7, wherein the step (A) further comprises the steps of

(a) raising red-green-blue values of the image to a predetermined power;

(b) performing a standard luminance-chrominance conversion;

(c) creating the mask.